Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision

Wednesday 8 April

Computer Vision

Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis

Jintao Chen, Chengyu Bai, Junjun Hu et al. (+2 more)

Autoregressive video synthesis offers a promising pathway for infinite-horizon generation but is fundamentally hindered by three intertwined challenges: semantic forgetting from context limitations, visual drift due to positional extrapolation, and controllability loss during interactive instruction switching. Current methods often tackle these issues in isolation, limiting long-term coherence. We introduce Grounded Forcing, a novel framework that bridges time-independent semantics and proximal dynamics through three interlocking mechanisms. First, to address semantic forgetting, we propose a Dual Memory KV Cache that decouples local temporal dynamics from global semantic anchors, ensuring long-term semantic coherence and identity stability. Second, to suppress visual drift, we design Dual-Reference RoPE Injection, which confines positional embeddings within the training manifold while rendering global semantics time-invariant. Third, to resolve controllability issues, we develop Asymmetric Proximity Recache, which facilitates smooth semantic inheritance during prompt transitions via proximity-weighted cache updates. These components operate synergistically to tether the generative process to stable semantic cores while accommodating flexible local dynamics. Extensive experiments demonstrate that Grounded Forcing significantly enhances long-range consistency and visual stability, establishing a robust foundation for interactive long-form video synthesis.
Read the full abstract

All authors Jintao Chen, Chengyu Bai, Junjun Hu, Xinda Xue, Mu Xu

Computer Vision

POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP

Jiyun Won, Heemin Yang, Woohyeok Kim et al. (+2 more)

Recent work has explored optimizing image signal processing (ISP) pipelines for various tasks by composing predefined modules and adapting them to task-specific objectives. However, jointly optimizing module sequences and parameters remains challenging. Existing approaches rely on neural architecture search (NAS) or step-wise reinforcement learning (RL), but NAS suffers from a training-inference mismatch, while step-wise RL leads to unstable training and high computational overhead due to stage-wise decision-making. We propose POS-ISP, a sequence-level RL framework that formulates modular ISP optimization as a global sequence prediction problem. Our method predicts the entire module sequence and its parameters in a single forward pass and optimizes the pipeline using a terminal task reward, eliminating the need for intermediate supervision and redundant executions. Experiments across multiple downstream tasks show that POS-ISP improves task performance while reducing computational cost, highlighting sequence-level optimization as a stable and efficient paradigm for task-aware ISP. The project page is available at https://w1jyun.github.io/POS-ISP
Read the full abstract

All authors Jiyun Won, Heemin Yang, Woohyeok Kim, Jungseul Ok, Sunghyun Cho

Computer Vision

Multi-modal user interface control detection using cross-attention

Milad Moradi, Ke Yan, David Colwell et al. (+2 more)

Detecting user interface (UI) controls from software screenshots is a critical task for automated testing, accessibility, and software analytics, yet it remains challenging due to visual ambiguities, design variability, and the lack of contextual cues in pixel-only approaches. In this paper, we introduce a novel multi-modal extension of YOLOv5 that integrates GPT-generated textual descriptions of UI images into the detection pipeline through cross-attention modules. By aligning visual features with semantic information derived from text embeddings, our model enables more robust and context-aware UI control detection. We evaluate the proposed framework on a large dataset of over 16,000 annotated UI screenshots spanning 23 control classes. Extensive experiments compare three fusion strategies, i.e. element-wise addition, weighted sum, and convolutional fusion, demonstrating consistent improvements over the baseline YOLOv5 model. Among these, convolutional fusion achieved the strongest performance, with significant gains in detecting semantically complex or visually ambiguous classes. These results establish that combining visual and textual modalities can substantially enhance UI element detection, particularly in edge cases where visual information alone is insufficient. Our findings open promising opportunities for more reliable and intelligent tools in software testing, accessibility support, and UI analytics, setting the stage for future research on efficient, robust, and generalizable multi-modal detection systems.
Read the full abstract

All authors Milad Moradi, Ke Yan, David Colwell, Matthias Samwald, Rhona Asgari

Computer Vision · Cross-listed from cs.LG

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

Yitong Li, Junsong Chen, Shuchen Xue et al. (+8 more)

Reinforcement-Learning-based post-training has recently emerged as a promising paradigm for aligning text-to-image diffusion models with human preferences. In recent studies, increasing the rollout group size yields pronounced performance improvements, indicating substantial room for further alignment gains. However, scaling rollouts on large-scale foundational diffusion models (e.g., FLUX.1-12B) imposes a heavy computational burden. To alleviate this bottleneck, we explore the integration of FP4 quantization into Diffusion RL rollouts. Yet, we identify that naive quantized pipelines inherently introduce risks of performance degradation. To overcome this dilemma between efficiency and training integrity, we propose Sol-RL (Speed-of-light RL), a novel FP4-empowered Two-stage Reinforcement Learning framework. First, we utilize high-throughput NVFP4 rollouts to generate a massive candidate pool and extract a highly contrastive subset. Second, we regenerate these selected samples in BF16 precision and optimize the policy exclusively on them. By decoupling candidate exploration from policy optimization, Sol-RL integrates the algorithmic mechanisms of rollout scaling with the system-level throughput gains of NVFP4. This synergistic algorithm-hardware design effectively accelerates the rollout phase while reserving high-fidelity samples for optimization. We empirically demonstrate that our framework maintains the training integrity of BF16 precision pipeline while fully exploiting the throughput gains enabled by FP4 arithmetic. Extensive experiments across SANA, FLUX.1, and SD3.5-L substantiate that our approach delivers superior alignment performance across multiple metrics while accelerating training convergence by up to $4.64\times$, unlocking the power of massive rollout scaling at a fraction of the cost.
Read the full abstract

All authors Yitong Li, Junsong Chen, Shuchen Xue, Pengcuo Zeren, Siyuan Fu, Dinghao Yang, Yangyang Tang, Junjie Bai, Ping Luo, Song Han, Enze Xie

Computer Vision

Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models

Yuheng Shi, Xiaohuan Pei, Linfeng Wen et al. (+2 more)

MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indiscriminately flood the quadratic self-attention mechanism with visually redundant tokens, severely bottlenecking inference throughput while ignoring spatial sparsity and query intent. To overcome this, we propose Q-Zoom, a query-aware adaptive high-resolution perception framework that operates in an efficient coarse-to-fine manner. First, a lightweight Dynamic Gating Network safely bypasses high-resolution processing when coarse global features suffice. Second, for queries demanding fine-grained perception, a Self-Distilled Region Proposal Network (SD-RPN) precisely localizes the task-relevant Region-of-Interest (RoI) directly from intermediate feature spaces. To optimize these modules efficiently, the gating network uses a consistency-aware generation strategy to derive deterministic routing labels, while the SD-RPN employs a fully self-supervised distillation paradigm. A continuous spatio-temporal alignment scheme and targeted fine-tuning then seamlessly fuse the dense local RoI with the coarse global layout. Extensive experiments demonstrate that Q-Zoom establishes a dominant Pareto frontier. Using Qwen2.5-VL-7B as a primary testbed, Q-Zoom accelerates inference by 2.52 times on Document & OCR benchmarks and 4.39 times in High-Resolution scenarios while matching the baseline's peak accuracy. Furthermore, when configured for maximum perceptual fidelity, Q-Zoom surpasses the baseline's peak performance by 1.1% and 8.1% on these respective benchmarks. These robust improvements transfer seamlessly to Qwen3-VL, LLaVA, and emerging RL-based thinking-with-image models. Project page is available at https://yuhengsss.github.io/Q-Zoom/.
Read the full abstract

All authors Yuheng Shi, Xiaohuan Pei, Linfeng Wen, Minjing Dong, Chang Xu

Computer Vision · Cross-listed from cs.CE

XR-CareerAssist: An Immersive Platform for Personalised Career Guidance Leveraging Extended Reality and Multimodal AI

N.D. Tantaroudas, A.J. McCracken, I. Karachalios et al. (+2 more)

Conventional career guidance platforms rely on static, text-driven interfaces that struggle to engage users or deliver personalised, evidence-based insights. Although Computer-Assisted Career Guidance Systems have evolved since the 1960s, they remain limited in interactivity and pay little attention to the narrative dimensions of career development. We introduce XR-CareerAssist, a platform that unifies Extended Reality (XR) with several Artificial Intelligence (AI) modules to deliver immersive, multilingual career guidance. The system integrates Automatic Speech Recognition for voice-driven interaction, Neural Machine Translation across English, Greek, French, and Italian, a Langchain-based conversational Training Assistant for personalised dialogue, a BLIP-based Vision-Language model for career visualisations, and AWS Polly Text-to-Speech delivered through an interactive 3D avatar. Career trajectories are rendered as dynamic Sankey diagrams derived from a repository of more than 100,000 anonymised professional profiles. The application was built in Unity for Meta Quest 3, with backend services hosted on AWS. A pilot evaluation at the University of Exeter with 23 participants returned 95.6% speech recognition accuracy, 78.3% overall user satisfaction, and 91.3% favourable ratings for system responsiveness, with feedback informing subsequent improvements to motion comfort, audio clarity, and text legibility. XR-CareerAssist demonstrates how the fusion of XR and AI can produce more engaging, accessible, and effective career development tools, with the integration of five AI modules within a single immersive environment yielding a multimodal interaction experience that distinguishes it from existing career guidance platforms.
Read the full abstract

All authors N.D. Tantaroudas, A.J. McCracken, I. Karachalios, E. Papatheou, V. Pastrikakis

Computer Vision

Energy-Regularized Spatial Masking: A Novel Approach to Enhancing Robustness and Interpretability in Vision Models

Tom Devynck, Bilal Faye, Djamel Bouchaffra et al. (+3 more)

Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant computational redundancy and encourages reliance on spurious background correlations. As a result, modern vision models remain brittle and difficult to interpret. We propose Energy-Regularized Spatial Masking (ERSM), a novel framework that reformulates feature selection as a differentiable energy minimization problem. By embedding a lightweight Energy-Mask Layer inside standard convolutional backbones, each visual token is assigned a scalar energy composed of two competing forces: an intrinsic Unary importance cost and a Pairwise spatial coherence penalty. Unlike prior pruning methods that enforce rigid sparsity budgets or rely on heuristic importance scores, ERSM allows the network to autonomously discover an optimal information-density equilibrium tailored to each input. We validate ERSM on convolutional architectures and demonstrate that it produces emergent sparsity, improved robustness to structured occlusion, and highly interpretable spatial masks, while preserving classification accuracy. Furthermore, we show that the learned energy ranking significantly outperforms magnitude-based pruning in deletion-based robustness tests, revealing ERSM as an intrinsic denoising mechanism that isolates semantic object regions without pixel-level supervision.
Read the full abstract

All authors Tom Devynck, Bilal Faye, Djamel Bouchaffra, Nadjib Lazaar, Hanane Azzag, Mustapha Lebbah

Computer Vision

Time-driven Survival Analysis from FDG-PET/CT in Non-Small Cell Lung Cancer

Sambit Tarai, Ashish Chauhan, Elin Lundström et al. (+5 more)

Purpose: Automated medical image-based prediction of clinical outcomes, such as overall survival (OS), has great potential in improving patient prognostics and personalized treatment planning. We developed a deep regression framework using tissue-wise FDG-PET/CT projections as input, along with a temporal input representing a scalar time horizon (in days) to predict OS in patients with Non-Small Cell Lung Cancer (NSCLC). Methods: The proposed framework employed a ResNet-50 backbone to process input images and generate corresponding image embeddings. The embeddings were then combined with temporal data to produce OS probabilities as a function of time, effectively parameterizing the predictions based on time. The overall framework was developed using the U-CAN cohort (n = 556) and evaluated by comparing with a baseline method on the test set (n = 292). The baseline utilized the ResNet-50 architecture, processing only the images as input and providing OS predictions at pre-specified intervals, such as 2- or 5-year. Results: The incorporation of temporal data with image embeddings demonstrated an advantage in predicting OS, outperforming the baseline method with an improvement in AUC of 4.3%. The proposed model using clinical + IDP features achieved strong performance, and an ensemble of imaging and clinical + IDP models achieved the best overall performance (0.788), highlighting the complementary value of multimodal inputs. The proposed method also enabled risk stratification of patients into distinct categories (high vs low risk). Heat maps from the saliency analysis highlighted tumor regions as key structures for the prediction. Conclusion: Our method provided an automated framework for predicting OS as a function of time and demonstrates the potential of combining imaging and tabular data for improved survival prediction.
Read the full abstract

All authors Sambit Tarai, Ashish Chauhan, Elin Lundström, Johan Öfverstedt, Therese Sjöholm, Veronica Sanchez Rodriguez, Håkan Ahlström, Joel Kullberg

Computer Vision

SCT-MOT: Enhancing Air-to-Air Multiple UAVs Tracking with Swarm-Coupled Motion and Trajectory Guidance

Zhaochen Chu, Tao Song, Ren Jin et al. (+3 more)

Air-to-air tracking of swarm UAVs presents significant challenges due to the complex nonlinear group motion and weak visual cues for small objects, which often cause detection failures, trajectory fragmentation, and identity switches. Although existing methods have attempted to improve performance by incorporating trajectory prediction, they model each object independently, neglecting the swarm-level motion dependencies. Their limited integration between motion prediction and appearance representation also weakens the spatio-temporal consistency required for tracking in visually ambiguous and cluttered environments, making it difficult to maintain coherent trajectories and reliable associations. To address these challenges, we propose SCT-MOT, a tracking framework that integrates Swarm-Coupled motion modeling and Trajectory-guided feature fusion. First, we develop a Swarm Motion-Aware Trajectory Prediction (SMTP) module jointly models historical trajectories and posture-aware appearance features from a swarm-level perspective, enabling more accurate forecasting of the nonlinear, coupled group trajectories. Second, we design a Trajectory-Guided Spatio-Temporal Feature Fusion (TG-STFF) module aligns predicted positions with historical visual cues and deeply integrates them with current frame features, enhancing temporal consistency and spatial discriminability for weak objects. Extensive experiments on three public air-to-air swarm UAV tracking datasets, including AIRMOT, MOT-FLY, and UAVSwarm, demonstrate that SMTP achieves more accurate trajectory forecasts and yields a 1.21% IDF1 improvement over the state-of-the-art trajectory prediction module EqMotion when integrated into the same MOT framework. Overall, our SCT-MOT consistently achieves superior accuracy and robustness compared to state-of-the-art trackers across multiple metrics under complex swarm scenarios.
Read the full abstract

All authors Zhaochen Chu, Tao Song, Ren Jin, Shaoming He, Defu Lin, Siqing Cheng

Computer Vision

RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details

Dewei Zhou, You Li, Zongxin Yang et al. (+1 more)

We introduce region-specific image refinement as a dedicated problem setting: given an input image and a user-specified region (e.g., a scribble mask or a bounding box), the goal is to restore fine-grained details while keeping all non-edited pixels strictly unchanged. Despite rapid progress in image generation, modern models still frequently suffer from local detail collapse (e.g., distorted text, logos, and thin structures). Existing instruction-driven editing models emphasize coarse-grained semantic edits and often either overlook subtle local defects or inadvertently change the background, especially when the region of interest occupies only a small portion of a fixed-resolution input. We present RefineAnything, a multimodal diffusion-based refinement model that supports both reference-based and reference-free refinement. Building on a counter-intuitive observation that crop-and-resize can substantially improve local reconstruction under a fixed VAE input resolution, we propose Focus-and-Refine, a region-focused refinement-and-paste-back strategy that improves refinement effectiveness and efficiency by reallocating the resolution budget to the target region, while a blended-mask paste-back guarantees strict background preservation. We further introduce a boundary-aware Boundary Consistency Loss to reduce seam artifacts and improve paste-back naturalness. To support this new setting, we construct Refine-30K (20K reference-based and 10K reference-free samples) and introduce RefineEval, a benchmark that evaluates both edited-region fidelity and background consistency. On RefineEval, RefineAnything achieves strong improvements over competitive baselines and near-perfect background preservation, establishing a practical solution for high-precision local refinement. Project Page: https://limuloo.github.io/RefineAnything/.
Read the full abstract

All authors Dewei Zhou, You Li, Zongxin Yang, Yi Yang

Computer Vision

Physical Adversarial Attacks on AI Surveillance Systems:Detection, Tracking, and Visible–Infrared Evasion

Miguel A.DelaCruz, Patricia Mae Santos and Rafael T.Navarro

Physical adversarial attacks are increasingly studied in settings that resemble deployed surveillance systems rather than isolated image benchmarks. In these settings, person detection, multi-object tracking, visible–infrared sensing, and the practical form of the attack carrier all matter at once. This changes how the literature should be read. A perturbation that suppresses a detector in one frame may have limited practical effect if identity is recovered over time; an RGB-only result may say little about night-time systems that rely on visible and thermal inputs together; and a conspicuous patch can imply a different threat model from a wearable or selectively activated carrier. This paper reviews physical attacks from that surveillance-oriented viewpoint. Rather than attempting a complete catalogue of all physical attacks in computer vision, we focus on the technical questions that become central in surveillance: temporal persistence, sensing modality, carrier realism, and system-level objective. We organize prior work through a four-part taxonomy and discuss how recent results on multi-object tracking, dual-modal visible–infrared evasion, and controllable clothing reflect a broader change in the field. We also summarize evaluation practices and unresolved gaps, including distance robustness, camera-pipeline variation, identity-level metrics, and activation-aware testing. The resulting picture is that surveillance robustness cannot be judged reliably from isolated per-frame benchmarks alone; it has to be examined as a system problem unfolding over time, across sensors, and under realistic physical deployment constraints.
Read the full abstract

Computer Vision

Vision-Language Model-Guided Deep Unrolling Enables Personalized, Fast MRI

Fangmao Ju, Yuzhu He, Zhiwen Xue et al. (+2 more)

Magnetic Resonance Imaging (MRI) is a cornerstone in medicine and healthcare but suffers from long acquisition times. Traditional accelerated MRI methods optimize for generic image quality, lacking adaptability for specific clinical tasks. To address this, we introduce PASS (Personalized, Anomaly-aware Sampling and reconStruction), an intelligent MRI framework that leverages a Vision-Language Model (VLM) to guide a deep unrolling network for task-oriented, fast imaging. PASS dynamically personalizes the imaging pipeline through three core contributions: (1) a deep unrolled reconstruction network derived from a physics-based MRI model; (2) a sampling module that generates patient-specific $k$-space trajectories; and (3) an anomaly-aware prior, extracted from a pretrained VLM, which steers both sampling and reconstruction toward clinically relevant regions. By integrating the high-level clinical reasoning of a VLM with an interpretable, physics-aware network, PASS achieves superior image quality across diverse anatomies, contrasts, anomalies, and acceleration factors. This enhancement directly translates to improvements in downstream diagnostic tasks, including fine-grained anomaly detection, localization, and diagnosis.
Read the full abstract

All authors Fangmao Ju, Yuzhu He, Zhiwen Xue, Chunfeng Lian, Jianhua Ma

Computer Vision

CloudMamba: An Uncertainty-Guided Dual-Scale Mamba Network for Cloud Detection in Remote Sensing Imagery

Jiajun Yang, Keyan Chen, Zhengxia Zou et al. (+1 more)

Cloud detection in remote sensing imagery is a fundamental, critical, and highly challenging problem. Existing deep learning-based cloud detection methods generally formulate it as a single-stage pixel-wise binary segmentation task with one forward pass. However, such single-stage approaches exhibit ambiguity and uncertainty in thin-cloud regions and struggle to accurately handle fragmented clouds and boundary details. In this paper, we propose a novel deep learning framework termed CloudMamba. To address the ambiguity in thin-cloud regions, we introduce an uncertainty-guided two-stage cloud detection strategy. An embedded uncertainty estimation module is proposed to automatically quantify the confidence of thin-cloud segmentation, and a second-stage refinement segmentation is introduced to improve the accuracy in low-confidence hard regions. To better handle fragmented clouds and fine-grained boundary details, we design a dual-scale Mamba network based on a CNN-Mamba hybrid architecture. Compared with Transformer-based models with quadratic computational complexity, the proposed method maintains linear computational complexity while effectively capturing both large-scale structural characteristics and small-scale boundary details of clouds, enabling accurate delineation of overall cloud morphology and precise boundary segmentation. Extensive experiments conducted on the GF1_WHU and Levir_CS public datasets demonstrate that the proposed method outperforms existing approaches across multiple segmentation accuracy metrics, while offering high efficiency and process transparency. Our code is available at https://github.com/jayoungo/CloudMamba.
Read the full abstract

All authors Jiajun Yang, Keyan Chen, Zhengxia Zou, Zhenwei Shi

Computer Vision

VGGT-SLAM++

Avilasha Mandal, Rajesh Kumar, Sudarshan Sunil Harithas et al. (+1 more)

We introduce VGGT-SLAM++, a complete visual SLAM system that leverages the geometry-rich outputs of the Visual Geometry Grounded Transformer (VGGT). The system comprises a visual odometry (front-end) fusing the VGGT feed-forward transformer and a Sim(3) solution, a Digital Elevation Map (DEM)-based graph construction module, and a back-end that jointly enable accurate large-scale mapping with bounded memory. While prior transformer-based SLAM pipelines such as VGGT-SLAM rely primarily on sparse loop closures or global Sim(3) manifold constraints - allowing short-horizon pose drift - VGGT-SLAM++ restores high-cadence local bundle adjustment (LBA) through a spatially corrective back-end. For each VGGT submap, we construct a dense planar-canonical DEM, partition it into patches, and compute their DINOv2 embeddings to integrate the submap into a covisibility graph. Spatial neighbors are retrieved using a Visual Place Recognition (VPR) module within the covisibility window, triggering frequent local optimization that stabilizes trajectories. Across standard SLAM benchmarks, VGGT-SLAM++ achieves state-of-the-art accuracy, substantially reducing short-term drift, accelerating graph convergence, and maintaining global consistency with compact DEM tiles and sublinear retrieval.
Read the full abstract

All authors Avilasha Mandal, Rajesh Kumar, Sudarshan Sunil Harithas, Chetan Arora

Computer Vision

RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation

Donghyeon Kwon, Taegyu Park and Suha Kwak

Semi-supervised learning for LiDAR semantic segmentation often suffers from error propagation and confirmation bias caused by noisy pseudo-labels. To tackle this chronic issue, we introduce RePL, a novel framework that enhances pseudo-label quality by identifying and correcting potential errors in pseudo-labels through masked reconstruction, along with a dedicated training strategy. We also provide a theoretical analysis demonstrating the condition under which the pseudo-label refinement is beneficial, and empirically confirm that the condition is mild and clearly met by RePL. Extensive evaluations on the nuScenes-lidarseg and SemanticKITTI datasets show that RePL improves pseudo-label quality substantially, and in consequence, achieves the state of the art in semi-supervised LiDAR semantic segmentation.
Read the full abstract

Computer Vision

Generate, Analyze, and Refine: Training-Free Sound Source Localization via MLLM Meta-Reasoning

Subin Park and Jung Uk Kim

Sound source localization task aims to identify the locations of sound-emitting objects by leveraging correlations between audio and visual modalities. Most existing SSL methods rely on contrastive learning-based feature matching, but lack explicit reasoning and verification, limiting their effectiveness in complex acoustic scenes. Inspired by human meta-cognitive processes, we propose a training-free SSL framework that exploits the intrinsic reasoning capabilities of Multimodal Large Language Models (MLLMs). Our Generation-Analysis-Refinement (GAR) pipeline consists of three stages: Generation produces initial bounding boxes and audio classifications; Analysis quantifies Audio-Visual Consistency via open-set role tagging and anchor voting; and Refinement applies adaptive gating to prevent unnecessary adjustments. Extensive experiments on single-source and multi-source benchmarks demonstrate competitive performance. The source code is available at https://github.com/VisualAIKHU/GAR-SSL.
Read the full abstract

Computer Vision · Cross-listed from physics.optics

Enhanced Self-Supervised Multi-Image Super-Resolution for Camera Array Images

Yating Chen, Feng Huang, Xianyu Wu et al. (+2 more)

Conventional multi-image super-resolution (MISR) methods, such as burst and video SR, rely on sequential frames from a single camera. Consequently, they suffer from complex image degradation and severe occlusion, increasing the difficulty of accurate image restoration. In contrast, multi-aperture camera-array imaging captures spatially distributed views with sampling offsets forming a stable disk-like distribution, which enhances the non-redundancy of observed data. Existing MISR algorithms fail to fully exploit these unique properties. Supervised MISR methods tend to overfit the degradation patterns in training data, and current self-supervised learning (SSL) techniques struggle to recover fine-grained details. To address these issues, this paper thoroughly investigates the strengths, limitations and applicability boundaries of multi-image-to-single-image (Multi-to-Single) and multi-image-to-multi-image (Multi-to-Multi) SSL methods. We propose the Multi-to-Single-Guided Multi-to-Multi SSL framework that combines the advantages of Multi-to-Single and Multi-to-Multi to generate visually appealing and high-fidelity images rich in texture details. The Multi-to-Single-Guided Multi-to-Multi SSL framework provides a new paradigm for integrating deep neural network with classical physics-based variational methods. To enhance the ability of MISR network to recover high-frequency details from aliased artifacts, this paper proposes a novel camera-array SR network called dual Transformer suitable for SSL. Experiments on synthetic and real-world datasets demonstrate the superiority of the proposed method.
Read the full abstract

All authors Yating Chen, Feng Huang, Xianyu Wu, Jing Wu, Ying Shen

Computer Vision

FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift

Huy Q. Le, Loc X. Nguyen, Yu Qiao et al. (+3 more)

Federated Learning (FL) enables decentralized model training across multiple clients without exposing private data, making it ideal for privacy-sensitive applications. However, in real-world FL scenarios, clients often hold data from distinct domains, leading to severe domain shift and degraded global model performance. To address this, prototype learning has been emerged as a promising solution, which leverages class-wise feature representations. Yet, existing methods face two key limitations: (1) Existing prototype-based FL methods typically construct a $\textit{single global prototype}$ per class by aggregating local prototypes from all clients without preserving domain information. (2) Current feature-prototype alignment is $\textit{domain-agnostic}$, forcing clients to align with global prototypes regardless of domain origin. To address these challenges, we propose Federated Domain-Aware Prototypes (FedDAP) to construct domain-specific global prototypes by aggregating local client prototypes within the same domain using a similarity-weighted fusion mechanism. These global domain-specific prototypes are then used to guide local training by aligning local features with prototypes from the same domain, while encouraging separation from prototypes of different domains. This dual alignment enhances domain-specific learning at the local level and enables the global model to generalize across diverse domains. Finally, we conduct extensive experiments on three different datasets: DomainNet, Office-10, and PACS to demonstrate the effectiveness of our proposed framework to address the domain shift challenges. The code is available at https://github.com/quanghuy6997/FedDAP.
Read the full abstract

All authors Huy Q. Le, Loc X. Nguyen, Yu Qiao, Seong Tae Kim, Eui-Nam Huh, Choong Seon Hong

Computer Vision

Video-guided Machine Translation with Global Video Context

Jian Chen, JinZe Lv, Zi Long et al. (+1 more)

Video-guided Multimodal Translation (VMT) has advanced significantly in recent years. However, most existing methods rely on locally aligned video segments paired one-to-one with subtitles, limiting their ability to capture global narrative context across multiple segments in long videos. To overcome this limitation, we propose a globally video-guided multimodal translation framework that leverages a pretrained semantic encoder and vector database-based subtitle retrieval to construct a context set of video segments closely related to the target subtitle semantics. An attention mechanism is employed to focus on highly relevant visual content, while preserving the remaining video features to retain broader contextual information. Furthermore, we design a region-aware cross-modal attention mechanism to enhance semantic alignment during translation. Experiments on a large-scale documentary translation dataset demonstrate that our method significantly outperforms baseline models, highlighting its effectiveness in long-video scenarios.
Read the full abstract

All authors Jian Chen, JinZe Lv, Zi Long, XiangHua Fu

Computer Vision

Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer

Bohao Xing, Deng Li, Rong Gao et al. (+2 more)

Recently, Transformer has made significant progress in various vision tasks. To balance computation and efficiency in video tasks, recent works heavily rely on factorized or window-based self-attention. However, these approaches split spatiotemporal correlations between regions of interest in videos, limiting the models' ability to capture motion and long-range dependencies. In this paper, we argue that, similar to the human visual system, the importance of temporal and spatial information varies across different time scales, and attention is allocated sparsely over time through glance and gaze behavior. Is equal consideration of time and space crucial for success in video tasks? Motivated by this understanding, we propose a dual-path network called the Overall Glance and Refined Gaze (OG-ReG) Transformer. The Glance path extracts coarse-grained overall spatiotemporal information, while the Gaze path supplements the Glance path by providing local details. Our model achieves state-of-the-art results on the Kinetics-400, Something-Something v2, and Diving-48, demonstrating its competitive performance. The code will be available at https://github.com/linuxsino/OG-ReG.
Read the full abstract

All authors Bohao Xing, Deng Li, Rong Gao, Xin Liu, Heikki Kälviäinen

Computer Vision

EventFace: Event-Based Face Recognition via Structure-Driven Spatiotemporal Modeling

Qingguo Meng, Xingbo Dong, Zhe Jin et al. (+1 more)

Event cameras offer a promising sensing modality for face recognition due to their inherent advantages in illumination robustness and privacy-friendliness. However, because event streams lack the stable photometric appearance relied upon by conventional RGB-based face recognition systems, we argue that event-based face recognition should model structure-driven spatiotemporal identity representations shaped by rigid facial motion and individual facial geometry. Since dedicated datasets for event-based face recognition remain lacking, we construct EFace, a small-scale event-based face dataset captured under rigid facial motion. To learn effectively from this limited event data, we further propose EventFace, a framework for event-based face recognition that integrates spatial structure and temporal dynamics for identity modeling. Specifically, we employ Low-Rank Adaptation (LoRA) to transfer structural facial priors from pretrained RGB face models to the event domain, thereby establishing a reliable spatial basis for identity modeling. Building on this foundation, we further introduce a Motion Prompt Encoder (MPE) to explicitly encode temporal features and a Spatiotemporal Modulator (STM) to fuse them with spatial features, thereby enhancing the representation of identity-relevant event patterns. Extensive experiments demonstrate that EventFace achieves the best performance among the evaluated baselines, with a Rank-1 identification rate of 94.19% and an equal error rate (EER) of 5.35%. Results further indicate that EventFace exhibits stronger robustness under degraded illumination than the competing methods. In addition, the learned representations exhibit reduced template reconstructability.
Read the full abstract

All authors Qingguo Meng, Xingbo Dong, Zhe Jin, Massimo Tistarelli

Computer Vision

Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization

Wenhao Yang, Yu Xia, Jinlong Huang et al. (+10 more)

Recent advancements in Multimodal Large Language Models (MLLMs) have incentivized models to “think with images” by actively invoking visual tools during multi-turn reasoning. The common Reinforcement Learning (RL) practice of relying on outcome-based rewards ignores the fact that textual plausibility often masks executive failure, meaning that models may exhibit intuitive textual reasoning while executing imprecise or irrelevant visual actions within their agentic reasoning trajectories. This reasoning-action discrepancy introduces noise that accumulates throughout the multi-turn reasoning process, severely degrading the model's multimodal reasoning capabilities and potentially leading to training collapse. In this paper, we introduce Multimodal Agentic Policy Optimization (MAPO), bridging the gap between textual reasoning and visual actions generated by models within their Multimodal Chain-of-Thought (MCoT). Specifically, MAPO mandates the model to generate explicit textual descriptions for the visual content obtained via tool usage. We then employ a novel advantage estimation that couples the semantic alignment between these descriptions and the actual observations with the task reward. Theoretical findings are provided to justify the rationale behind MAPO, which inherently reduces the variance of gradients, and extensive experiments demonstrate that our method achieves superior performance across multiple visual reasoning benchmarks.
Read the full abstract

All authors Wenhao Yang, Yu Xia, Jinlong Huang, Shiyin Lu, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Yuchen Zhou, Xiaobo Xia, Yuanyu Wan, Lijun Zhang, Tat-Seng Chua

Computer Vision

FlowExtract: Procedural Knowledge Extraction from Maintenance Flowcharts

Guillermo Gil de Avalle, Laura Maruster, Eric Sloot et al. (+1 more)

Maintenance procedures in manufacturing facilities are often documented as flowcharts in static PDFs or scanned images. They encode procedural knowledge essential for asset lifecycle management, yet inaccessible to modern operator support systems. Vision-language models, the dominant paradigm for image understanding, struggle to reconstruct connection topology from such diagrams. We present FlowExtract, a pipeline for extracting directed graphs from ISO 5807-standardized flowcharts. The system separates element detection from connectivity reconstruction, using YOLOv8 and EasyOCR for standard domain-aligned node detection and text extraction, combined with a novel edge detection method that analyzes arrowhead orientations and traces connecting lines backward to source nodes. Evaluated on industrial troubleshooting guides, FlowExtract achieves very high node detection and substantially outperforms vision-language model baselines on edge extraction, offering organizations a practical path toward queryable procedural knowledge representations. The implementation is available athttps://github.com/guille-gil/FlowExtract.
Read the full abstract

All authors Guillermo Gil de Avalle, Laura Maruster, Eric Sloot, Christos Emmanouilidis

Computer Vision

FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching

Junchao Yi, Rui Zhao, Jiahao Tang et al. (+7 more)

Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We challenge this paradigm by asking whether all modalities, including textual descriptions, spatial layouts, and editing instructions, can be unified into a single visual representation. We present FlowInOne, a framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean image-in, image-out pipeline governed by a single flow matching model. This vision-centric formulation naturally eliminates cross-modal alignment bottlenecks, noise scheduling, and task-specific architectural branches, unifying text-to-image generation, layout-guided editing, and visual instruction following under one coherent paradigm. To support this, we introduce VisPrompt-5M, a large-scale dataset of 5 million visual prompt pairs spanning diverse tasks including physics-aware force dynamics and trajectory prediction, alongside VP-Bench, a rigorously curated benchmark assessing instruction faithfulness, spatial precision, visual realism, and content consistency. Extensive experiments demonstrate that FlowInOne achieves state-of-the-art performance among open-source models across all unified generation tasks while remaining competitive with leading commercial systems, thereby establishing a new foundation for fully vision-centric generative modeling, in which perception and creation coexist within a unified continuous visual space. Our code and models are released on https://csu-jpg.github.io/FlowInOne.github.io/
Read the full abstract

All authors Junchao Yi, Rui Zhao, Jiahao Tang, Weixian Lei, Linjie Li, Qisheng Su, Zhengyuan Yang, Lijuan Wang, Xiaofeng Zhu, Alex Jinpeng Wang

Computer Vision

How Well Do Vision-Language Models Understand Sequential Driving Scenes? A Sensitivity Study

Roberto Brusnicki, Mattia Piccinini and Johannes Betz

Vision-Language Models (VLMs) are increasingly proposed for autonomous driving tasks, yet their performance on sequential driving scenes remains poorly characterized, particularly regarding how input configurations affect their capabilities. We introduce VENUSS (VLM Evaluation oN Understanding Sequential Scenes), a framework for systematic sensitivity analysis of VLM performance on sequential driving scenes, establishing baselines for future research. Building upon existing datasets, VENUSS extracts temporal sequences from driving videos, and generates structured evaluations across custom categories. By comparing 25+ existing VLMs across 2,600+ scenarios, we reveal how even top models achieve only 57% accuracy, not matching human performance under similar constraints (65%) and exposing significant capability gaps. Our analysis shows that VLMs excel with static object detection but struggle with understanding vehicle dynamics and temporal relations. VENUSS offers the first systematic sensitivity analysis of VLMs focused on how input image configurations - resolution, frame count, temporal intervals, spatial layouts, and presentation modes - affect performance on sequential driving scenes. Supplementary material available at https://TUM-AVS.github.io/VENUSS/.
Read the full abstract

Computer Vision

From Static to Interactive: Adapting Visual in-Context Learners for User-Driven Tasks

Carlos Schmidt and Simon Reiß

Visual in-context learning models are designed to adapt to new tasks by leveraging a set of example input-output pairs, enabling rapid generalization without task-specific fine-tuning. However, these models operate in a fundamentally static paradigm: while they can adapt to new tasks, they lack any mechanism to incorporate user-provided guidance signals such as scribbles, clicks, or bounding boxes to steer or refine the prediction process. This limitation is particularly restrictive in real-world applications, where users want to actively guide model predictions, e.g., by highlighting the target object for segmentation, indicating a region which should be visually altered, or isolating a specific person in a complex scene to run targeted pose estimation. In this work, we propose a simple method to transform static visual in-context learners, particularly the DeLVM approach, into highly controllable, user-driven systems, i.e., Interactive DeLVM, enabling seamless interaction through natural visual cues such as scribbles, clicks, or drawing boxes. Specifically, by encoding interactions directly into the example input-output pairs, we keep the philosophy of visual in-context learning intact: enabling users to prompt models with unseen interactions without fine-tuning and empowering them to dynamically steer model predictions with personalized interactions. Our experiments demonstrate that SOTA visual in-context learning models fail to effectively leverage interaction cues, often ignoring user guidance entirely. In contrast, our method excels in controllable, user-guided scenarios, achieving improvements of $+7.95%$ IoU for interactive segmentation, $+2.46$ PSNR for directed super-resolution, and $-3.14%$ LPIPS for interactive object removal. With this, our work bridges the gap between rigid static task adaptation and fluid interactivity for user-centric visual in-context learning.
Read the full abstract

Computer Vision

LiveStre4m: Feed-Forward Live Streaming of Novel Views from Unposed Multi-View Video

Pedro Quesado, Erkut Akdag, Yasaman Kashefbahrami et al. (+2 more)

Live-streaming Novel View Synthesis (NVS) from unposed multi-view video remains an open challenge in a wide range of applications. Existing methods for dynamic scene representation typically require ground-truth camera parameters and involve lengthy optimizations ($\approx 2.67$s), which makes them unsuitable for live streaming scenarios. To address this issue, we propose a novel viewpoint video live-streaming method (LiveStre4m), a feed-forward model for real-time NVS from unposed sparse multi-view inputs. LiveStre4m introduces a multi-view vision transformer for keyframe 3D scene reconstruction coupled with a diffusion-transformer interpolation module that ensures temporal consistency and stable streaming. In addition, a Camera Pose Predictor module is proposed to efficiently estimate both poses and intrinsics directly from RGB images, removing the reliance on known camera calibration information. Our approach enables temporally consistent novel-view video streaming in real-time using as few as two synchronized unposed input streams. LiveStre4m attains an average reconstruction time of $ 0.07$s per-frame at $ 1024 \times 768$ resolution, outperforming the optimization-based dynamic scene representation methods by orders of magnitude in runtime. These results demonstrate that LiveStre4m makes real-time NVS streaming feasible in practical settings, marking a substantial step toward deployable live novel-view synthesis systems. Code available at: https://github.com/pedro-quesado/LiveStre4m
Read the full abstract

All authors Pedro Quesado, Erkut Akdag, Yasaman Kashefbahrami, Willem Menu, Egor Bondarev

Computer Vision

DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting

Hantang Li, Qiang Zhu, Xiandong Meng et al. (+2 more)

Sparse-view reconstruction with 3D Gaussian Splatting (3DGS) is fundamentally ill-posed due to insufficient geometric supervision, often leading to severe overfitting and the emergence of structural distortions and translucent haze-like artifacts. While existing approaches attempt to alleviate this issue via dropout-based regularization, they are largely heuristic and lack a unified understanding of artifact formation. In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective and identify the core challenge as the unobservability of Gaussian primitive reliability. Unreliable Gaussians are insufficiently constrained during optimization and accumulate as haze-like degradations in rendered images. Motivated by this observation, we propose a unified Dual-domain Observation and Calibration (DOC-GS) framework that models and corrects Gaussian reliability through the synergy of optimization-domain inductive bias and observation-domain evidence. Specifically, in the optimization domain, we characterize Gaussian reliability by the degree to which each primitive is constrained during training, and instantiate this signal via a Continuous Depth-Guided Dropout (CDGD) strategy, where the dropout probability serves as an explicit proxy for primitive reliability. This imposes a smooth depth-aware inductive bias to suppress weakly constrained Gaussians and improve optimization stability. In the observation domain, we establish a connection between floater artifacts and atmospheric scattering, and leverage the Dark Channel Prior (DCP) as a structural consistency cue to identify and accumulate anomalous regions. Based on cross-view aggregated evidence, we further design a reliability-driven geometric pruning strategy to remove low-confidence Gaussians.
Read the full abstract

All authors Hantang Li, Qiang Zhu, Xiandong Meng, Debin Zhao, Xiaopeng Fan

Computer Vision

URMF: Uncertainty-aware Robust Multimodal Fusion for Multimodal Sarcasm Detection

Zhenyu Wang, Weichen Cheng, Weijia Li et al. (+3 more)

Multimodal sarcasm detection (MSD) aims to identify sarcastic intent from semantic incongruity between text and image. Although recent methods have improved MSD through cross-modal interaction and incongruity reasoning, most still treat modalities as equally reliable. In real social media posts, however, text and images often differ in noise level and relevance, making deterministic fusion susceptible to noisy evidence and weakened incongruity cues. To address this issue, we propose Uncertainty-aware Robust Multimodal Fusion (URMF), a unified framework for robust MSD. URMF first injects visual evidence into textual representations through multi-head cross-attention, and then applies self-attention in the fused semantic space to enhance incongruity reasoning. It models textual, visual, and interaction-aware representations as learnable Gaussian posteriors to estimate modality-specific uncertainty. Based on the estimated uncertainty, URMF dynamically adjusts modality contributions during fusion to suppress unreliable evidence. We further optimize the model with a unified objective that combines information bottleneck regularization, modality prior regularization, cross-modal distribution alignment, and uncertainty-driven contrastive learning. Experiments on the public MSD and MMSD2 benchmarks show that URMF outperforms representative unimodal, multimodal, and MLLM-based baselines. The results demonstrate that explicit uncertainty modeling can improve both accuracy and robustness in multimodal sarcasm detection.
Read the full abstract

All authors Zhenyu Wang, Weichen Cheng, Weijia Li, Junjie Mou, Zongyou Zhao, Guoying Zhang

Computer Vision

Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning

Jiahua Chen, Qihong Tang, Weinong Wang et al. (+1 more)

Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either through computationally expensive post-training procedures on limited 3D datasets or through rigid tool-calling mechanisms that lack explicit geometric understanding and viewpoint flexibility. To address these challenges, we propose a training-free framework that introduces a Visual Chain-of-Thought mechanism grounded in explicit 3D reconstruction. The proposed pipeline first reconstructs a high-fidelity 3D mesh from a single image using MLLM-guided keyword extraction and mask generation at multiple granularities. Subsequently, the framework leverages an external knowledge base to iteratively compute optimal camera extrinsic parameters and synthesize novel views, thereby emulating human perspective-taking. Extensive experiments demonstrate that the proposed approach significantly enhances spatial comprehension. Specifically, the framework outperforms specialized spatial models and general-purpose MLLMs, including GPT-5.2 and Gemini-2.5-Flash, on major benchmarks such as 3DSRBench and Rel3D.
Read the full abstract

All authors Jiahua Chen, Qihong Tang, Weinong Wang, Qi Fan